{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T19:05:49Z","timestamp":1785179149739,"version":"3.55.0"},"reference-count":62,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Meta Platforms through Imperial College London","award":["P93445 (Cross-modal learning of emotions)"],"award-info":[{"award-number":["P93445 (Cross-modal learning of emotions)"]}]},{"DOI":"10.13039\/100004358","name":"Samsung","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100004358","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cybern."],"published-print":{"date-parts":[[2023,6]]},"DOI":"10.1109\/tcyb.2022.3162495","type":"journal-article","created":{"date-parts":[[2022,4,19]],"date-time":"2022-04-19T19:34:18Z","timestamp":1650396858000},"page":"3454-3466","source":"Crossref","is-referenced-by-count":36,"title":["End-to-End Video-to-Speech Synthesis Using Generative Adversarial Networks"],"prefix":"10.1109","volume":"53","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9493-3842","authenticated-orcid":false,"given":"Rodrigo","family":"Mira","sequence":"first","affiliation":[{"name":"Department of Computing, IBUG Group, Imperial College London, London, U.K"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Konstantinos","family":"Vougioukas","sequence":"additional","affiliation":[{"name":"Department of Computing, IBUG Group, Imperial College London, London, U.K"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pingchuan","family":"Ma","sequence":"additional","affiliation":[{"name":"Department of Computing, IBUG Group, Imperial College London, London, U.K"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stavros","family":"Petridis","sequence":"additional","affiliation":[{"name":"Department of Computing, IBUG Group, Imperial College London, London, U.K"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6478-8699","authenticated-orcid":false,"given":"Bj\u00f6rn W.","family":"Schuller","sequence":"additional","affiliation":[{"name":"Department of Computing, IBUG Group, Imperial College London, London, U.K"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maja","family":"Pantic","sequence":"additional","affiliation":[{"name":"Department of Computing, IBUG Group, Imperial College London, London, U.K"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953127"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.61"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01251-8"},{"key":"ref15","first-page":"5767","article-title":"Improved training of Wasserstein GANs","author":"gulrajani","year":"2017","journal-title":"Proc NeurIPS"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2009.2030637"},{"key":"ref14","article-title":"Generative adversarial networks","author":"goodfellow","year":"2014","journal-title":"arXiv 1406 2661"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/WOSSPA.2011.5931414"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref11","article-title":"End-to-end adversarial text-to-speech","author":"donahue","year":"2020","journal-title":"arXiv 2006 03575"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1445"},{"key":"ref10","first-page":"1","article-title":"Adversarial audio synthesis","author":"donahue","year":"2019","journal-title":"Proc ICLR"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3269"},{"key":"ref17","first-page":"4","article-title":"An efficient MFCC extraction method in speech recognition","author":"han","year":"2006","journal-title":"Proc Int Symp Circuits Syst"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2009.2026513"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2407694"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2013.2250954"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-85"},{"key":"ref46","first-page":"1060","article-title":"Generative adversarial text to image synthesis","volume":"48","author":"reed","year":"2016","journal-title":"Proc 33rd Int Conf Mach Learn (ICML)"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053569"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref47","first-page":"749","article-title":"Perceptual evaluation of speech quality (PESQ)-a new method for speech quality assessment of telephone networks and codecs","author":"rix","year":"2001","journal-title":"Proc ICASSP"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.161"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461326"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01381"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2020.01.022"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1669"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-139"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1121\/1.2229005"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2716178"},{"key":"ref4","article-title":"LipNet: End-to-end sentence-level lipreading","author":"assael","year":"2016","journal-title":"arXiv 1611 01599"},{"key":"ref3","article-title":"Wasserstein GAN","author":"arjovsky","year":"2017","journal-title":"arXiv 1701 07875"},{"key":"ref6","first-page":"87","article-title":"Lip reading in the wild","author":"chung","year":"2016","journal-title":"Proc Asian Conf Comput Vis"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3126686.3126723"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952625"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref34","article-title":"Conditional generative adversarial nets","author":"mirza","year":"2014","journal-title":"arXiv 1411 1784"},{"key":"ref37","first-page":"125","article-title":"WaveNet: A generative model for raw audio","author":"den van oord","year":"2016","journal-title":"Proc ISCA Speech Synth Workshop"},{"key":"ref36","first-page":"3915","article-title":"Parallel WaveNet: Fast high-fidelity speech synthesis","author":"den van oord","year":"2018","journal-title":"Proc ICML"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2726"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-19551-8_23"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1026"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2012-6"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2015.7163155"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461856"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2605"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.264"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.366941"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3241911"},{"key":"ref25","first-page":"14881","article-title":"MelGAN: Generative adversarial networks for conditional waveform synthesis","author":"kumar","year":"2019","journal-title":"Proc NeurIPS"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IAdCC.2013.6514336"},{"key":"ref21","first-page":"1755","article-title":"Dlib-ml: A machine learning toolkit","volume":"10","author":"king","year":"2009","journal-title":"J Mach Learn Res"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ISM.2018.00-19"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33012588"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1819"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00037"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.899236"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00374"}],"container-title":["IEEE Transactions on Cybernetics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6221036\/10128814\/09760273.pdf?arnumber=9760273","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,19]],"date-time":"2023-06-19T18:13:33Z","timestamp":1687198413000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9760273\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6]]},"references-count":62,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tcyb.2022.3162495","relation":{},"ISSN":["2168-2267","2168-2275"],"issn-type":[{"value":"2168-2267","type":"print"},{"value":"2168-2275","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6]]}}}